Combining driver alertness with advanced driver assistance systems (ADAS)

1. A method of calibrating a sensor of an advanced driver assistance system (ADAS) mechanism, comprising:

determining, by an ADAS mechanism, an offset between an angle of a potential obstacle relative to a first sensor of the ADAS mechanism, and a gaze angle of a user determined by a second sensor;

comparing, by the ADAS mechanism, a rate of change of the gaze angle during a period and a rate of change of the angle of the potential obstacle relative to the first sensor during the period;

determining, by the ADAS mechanism according to the comparing, a probability that a gaze of the user and the first sensor of the ADAS mechanism are both tracking the potential obstacle during the period; and

calibrating the second sensor for determining the gaze angle of the user, responsive to the determined probability.

2. The method of claim 1 , comprising determining the offset in response to a change in the user's position or orientation relative to at least one of the first sensor or the second sensor.

3. The method of claim 1 , wherein the rate of change of the gaze angle comprises a trajectory of the gaze angle, and the rate of change of the angle of the potential obstacle relative to the first sensor comprises a trajectory of the potential obstacle relative to the first sensor.

4. The method of claim 1 , further comprising:

determining a number of potential obstacles detected by the ADAS mechanism during the period; and

determining the probability that the gaze of the user and the first sensor of the ADAS mechanism are both tracking the potential obstacle, according to the comparing and to the number of potential obstacles detected by the ADAS mechanism.

5. The method of claim 1 , further comprising determining a trajectory difference TD=|(dE/dt−dA/dt)|, where dE/dt is the rate of change of the gaze angle during the period, and dA/dt is the rate of change of the angle of the potential obstacle relative to the first sensor during the period.

6. The method of claim 5 , comprising determining the probability according to 1/(TD+1)×1/N, where N is a number of potential obstacles detected by the ADAS mechanism during the period.

7. The method of claim 1 , further comprising:

comparing the determined probability against a predefined threshold; and

responsive to the determined probability being above the predefined threshold:

sampling the offset between the angle of a potential obstacle relative to the first sensor of the ADAS mechanism, and the gaze angle of a user determined by the second sensor; and

modeling the offset over time.

8. The method of claim 7 , wherein the offset is modeled over time according to:

Offset( t )= K ×Offset( t− 1)+(1− K )× SO,

where K is a smoothing parameter having a value in the range of 0.8 to 0.95, and SO is a sampled offset.

9. The method of claim 8 , comprising modeling the offset to generate estimates of the offset over time, and using the estimates to calibrate at least the second sensor.

10. The method of claim 1 , further comprising controlling, by the ADAS mechanism, an ADAS operation in response to the potential obstacle.

11. A system for calibrating a sensor of an advanced driver assistance system (ADAS) mechanism, comprising:

a first sensor of an ADAS mechanism configured to determine a potential obstacle to a vehicle, and an angle of the potential obstacle relative to the first sensor;

a second sensor configured to determine a gaze angle of a user; and

a calibration engine in communication with the first sensor and the second sensor, the calibration engine configured to:

determine an offset between the angle of the potential obstacle relative to the first sensor, and the gaze angle of the user determined by the second sensor;

compare a rate of change of the gaze angle during a period and a rate of change of the angle of the potential obstacle relative to the first sensor during the period;

determine, according to the comparing, a probability that a gaze of the user and the first sensor of the ADAS mechanism are both tracking the potential obstacle during the period; and

calibrate the second sensor for determining the gaze angle of the user, responsive to the determined probability.

12. The system of claim 11 , wherein the calibration engine is configured to determine the offset in response to a change in the user's position or orientation relative to at least one of the first sensor or the second sensor.

13. The system of claim 11 , wherein the rate of change of the gaze angle comprises a trajectory of the gaze angle, and the rate of change of the angle of the potential obstacle relative to the first sensor comprises a trajectory of the potential obstacle relative to the first sensor.

14. The system of claim 11 , wherein the calibration engine is further configured to:

determine a number of potential obstacles detected by the ADAS mechanism during the period; and

determine the probability that the gaze of the user and the first sensor of the ADAS mechanism are both tracking the potential obstacle, according to the comparing and to the number of potential obstacles detected by the ADAS mechanism.

15. The system of claim 11 , wherein the calibration engine is further configured to determine a trajectory difference TD=|(dE/dt−dA/dt)|, where dE/dt is the rate of change of the gaze angle during the period, and dA/dt is the rate of change of the angle of the potential obstacle relative to the first sensor during the period.

16. The system of claim 15 , wherein the calibration engine is configured to determine the probability according to 1/(TD+1)×1/N, where N is a number of potential obstacles detected by the ADAS mechanism during the period.

17. The system of claim 11 , wherein the calibration engine is further configured to:

compare the determined probability against a predefined threshold; and

responsive to the determined probability being above the predefined threshold:

sample the offset between the angle of a potential obstacle relative to the first sensor of the ADAS mechanism, and the gaze angle of a user determined by the second sensor; and

model the offset over time.

18. The system of claim 17 , wherein the calibration engine is configured to model the offset over time according to:

Offset( t )= K ×Offset( t −1)+(1− K )× SO,

where K is a smoothing parameter having a value in the range of 0.8 to 0.95, and SO is a sampled offset.

19. The system of claim 18 , wherein the calibration engine is configured to model the offset to generate estimates of the offset over time, and to use the estimates to calibrate at least the second sensor.

20. The system of claim 11 , wherein the ADAS mechanism is configured to initiate an ADAS operation in response to the potential obstacle.